Concept maps are visual summaries, structured as directed graphs: important concepts from a dataset are displayed as vertexes, and edges between vertexes show natural language descriptions of the relationships between the concepts on the map. Thus far, preliminary attempts at automatically creating concept maps have focused on building static summaries. However, in interactive settings, users will need to dynamically investigate particular relationships between pairs of concepts. For instance, a historian using a concept map browser might decide to investigate the relationship between two politicians in a news archive. We present a model which responds to such queries by returning one or more short, importance-ranked, natural language descriptions of the relationship between two requested concepts, for display in a visual interface. Our model is trained on a new public dataset, collected for this task.

We introduce a novel task, that of associating relative time with cities in text. We show that the task can be performed using NLP tools and techniques. The task is deployed on a large corpus of data to study a specific phenomenon, namely the temporal dimension of contemporary arts globalization over the first decade of the 21 st century.

No abstract